INDEX

Explanations

punctuation and formatting marks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tÄĽ

-0.16

rium

-0.15

ê²¬

-0.14

 mariage

-0.14

 remar

-0.14

 spos

-0.14

 Phen

-0.14

ayÄ±p

-0.14

Ø®Ø±

-0.14

çµĲå©ļ

-0.14

POSITIVE LOGITS

 villa

0.30

 Islanders

0.30

 Island

0.27

 island

0.26

 Villa

0.25

 Casa

0.24

villa

0.23

 Love

0.23

 contestants

0.22

 Contest

0.20

Activations Density 0.000%

punctuation and formatting marks

No Comments

No Known Activations

punctuation and formatting marks

No Comments

No Known Activations